Total runs:
16.3K
Run Growth:
7.0K
Growth Rate:
42.85%
Sponsored by
Vmake Labs Video Enhancer
voidful / Qwen3.5-9B-earica
Model's Last Updated: March 08 2026
image-text-to-text
Introduction of Qwen3.5-9B-earica
Model Details of Qwen3.5-9B-earica
See axolotl config
axolotl version:
0.16.0.dev0
# Example config for RCCA-TR A+ (Reliability-Calibrated Conflict-Aware Trust-Region) fine-tuning
# A+ variant: only 1 model in GPU memory (active model)
# Prior = offline cache, EMA = drift buffer
base_model: Qwen/Qwen3.5-9B
plugins:
- axolotl.integrations.rcca_tr.RCCATRPlugin
- axolotl.integrations.liger.LigerPlugin
liger_rms_norm: true
liger_glu_activation: true
# Enable RCCA-TR trainer
rcca_tr_trainer: true
# Conflict score hyperparameters
rcca_tr_conflict_lambda1: 1.0 # weight for surprisal in conflict score
rcca_tr_conflict_lambda2: 0.5 # weight for margin-based conflict
rcca_tr_conflict_tau: 1.0 # temperature for conflict sigmoid
# Reliability score hyperparameters
rcca_tr_reliability_beta: 0.5 # balance between stability and evidence
rcca_tr_reliability_tau: 1.0 # temperature for reliability sigmoid
# Trust-region hyperparameters
rcca_tr_epsilon_min: 0.01 # minimum trust-region radius
rcca_tr_epsilon_max: 1.0 # maximum trust-region radius
rcca_tr_kl_lambda: 1.0 # Lagrange multiplier for KL penalty
rcca_tr_use_smooth_objective: true # smooth g(r_t)*KL vs hinge
# Drift buffer (replaces EMA model)
rcca_tr_ema_decay: 0.999 # decay rate for drift buffer
rcca_tr_drift_gamma: 1.0 # drift → reliability scaling
# Prior cache (optional; omit to use fallback mode)
# rcca_tr_prior_cache_path: ./prior_cache/prior_cache.pt
# Dataset
datasets:
- path: voidful/earica_text_train
type: chat_template
field_messages: conversations
split: train
dataset_prepared_path: ./prepared_data/rcca_tr
chat_template: qwen3_5
# Training settings
sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5
bf16: true
gradient_checkpointing: true
flash_attention: true
dataloader_num_workers: 0
deepspeed: deepspeed_configs/zero2.json
val_set_size: 0.05
save_strategy: epoch
output_dir: ./outputs/rcca-tr-fft
hub_model_id: voidful/Qwen3.5-9B-earica
push_to_hub: true
hub_strategy: end
log_on_each_node: false
logging_steps: 1
Qwen3.5-9B-earica
This model is a fine-tuned version of Qwen/Qwen3.5-9B on the voidful/earica_text_train dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 80
- gradient_accumulation_steps: 4
- total_train_batch_size: 320
- total_eval_batch_size: 80
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 11
- training_steps: 375
Training results
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
Runs of voidful Qwen3.5-9B-earica on huggingface.co
17
Total runs
0
24-hour runs
2
3-day runs
2
7-day runs
15
30-day runs
More Information About Qwen3.5-9B-earica huggingface.co Model
Url of Qwen3.5-9B-earica
Qwen3.5-9B-earica huggingface.co Url
Provider of Qwen3.5-9B-earica huggingface.co
Other API from voidful
Updated:March 18 2023
Total runs:
1.5K
Run Growth:
1.5K
Growth Rate:
99.01%
Total runs:
984
Run Growth:
-1.3K
Growth Rate:
-133.07%
Total runs:
885
Run Growth:
0
Growth Rate:
0.00%
Total runs:
858
Run Growth:
-109
Growth Rate:
-13.92%
Total runs:
538
Run Growth:
505
Growth Rate:
93.87%
Total runs:
532
Run Growth:
92
Growth Rate:
21.60%
Total runs:
311
Run Growth:
0
Growth Rate:
0.00%
Total runs:
260
Run Growth:
-31
Growth Rate:
-11.92%
Total runs:
254
Run Growth:
0
Growth Rate:
0.00%
Total runs:
220
Run Growth:
220
Growth Rate:
100.00%
Total runs:
154
Run Growth:
34
Growth Rate:
23.61%
Total runs:
120
Run Growth:
67
Growth Rate:
54.92%
Total runs:
110
Run Growth:
72
Growth Rate:
64.29%
Total runs:
109
Run Growth:
35
Growth Rate:
32.11%
Total runs:
105
Run Growth:
78
Growth Rate:
72.90%
Total runs:
105
Run Growth:
35
Growth Rate:
32.41%
Total runs:
99
Run Growth:
-29
Growth Rate:
-29.29%
Total runs:
65
Run Growth:
57
Growth Rate:
87.69%
Total runs:
39
Run Growth:
16
Growth Rate:
38.10%
Total runs:
36
Run Growth:
-3
Growth Rate:
-8.33%
Total runs:
28
Run Growth:
12
Growth Rate:
42.86%
Total runs:
28
Run Growth:
12
Growth Rate:
38.71%
Total runs:
25
Run Growth:
15
Growth Rate:
60.00%
Total runs:
24
Run Growth:
2
Growth Rate:
7.69%
Total runs:
23
Run Growth:
9
Growth Rate:
37.50%
Total runs:
21
Run Growth:
14
Growth Rate:
58.33%
Total runs:
21
Run Growth:
2
Growth Rate:
8.70%
Total runs:
21
Run Growth:
16
Growth Rate:
64.00%
Total runs:
21
Run Growth:
14
Growth Rate:
63.64%
Total runs:
19
Run Growth:
19
Growth Rate:
100.00%
Total runs:
19
Run Growth:
12
Growth Rate:
63.16%
Total runs:
18
Run Growth:
11
Growth Rate:
50.00%
Total runs:
18
Run Growth:
13
Growth Rate:
72.22%
Total runs:
16
Run Growth:
12
Growth Rate:
75.00%
Total runs:
16
Run Growth:
6
Growth Rate:
30.00%
Total runs:
15
Run Growth:
-12
Growth Rate:
-80.00%
Total runs:
15
Run Growth:
2
Growth Rate:
10.53%
Total runs:
13
Run Growth:
11
Growth Rate:
78.57%
Total runs:
13
Run Growth:
10
Growth Rate:
71.43%
Total runs:
12
Run Growth:
-8
Growth Rate:
-66.67%
Total runs:
11
Run Growth:
2
Growth Rate:
14.29%
Total runs:
10
Run Growth:
8
Growth Rate:
66.67%
Total runs:
9
Run Growth:
7
Growth Rate:
77.78%
Total runs:
8
Run Growth:
1
Growth Rate:
11.11%
Total runs:
7
Run Growth:
-10
Growth Rate:
-142.86%
Total runs:
7
Run Growth:
7
Growth Rate:
87.50%
Total runs:
6
Run Growth:
-1
Growth Rate:
-14.29%
Total runs:
5
Run Growth:
-3
Growth Rate:
-60.00%
Total runs:
5
Run Growth:
5
Growth Rate:
100.00%
Total runs:
5
Run Growth:
-11
Growth Rate:
-220.00%